{
  "$schema": "https://raw.githubusercontent.com/jsonresume/resume-schema/master/schema.json",
  "basics": {
    "name": "Jason Doyle",
    "label": "Senior Software and Reliability Engineer",
    "email": "contact@jasondoyle.ie",
    "url": "https://jasondoyle.ie/",
    "summary": "Senior software and reliability engineer with more than a decade across Microsoft Office and Azure. Builds and operates distributed systems, data platforms and applied AI products.",
    "location": {
      "city": "Monroe",
      "region": "Washington",
      "countryCode": "US"
    },
    "profiles": [
      {
        "network": "GitHub",
        "username": "Jason-Doyle",
        "url": "https://github.com/Jason-Doyle"
      },
      {
        "network": "LinkedIn",
        "username": "jasondoyledev",
        "url": "https://www.linkedin.com/in/jasondoyledev"
      }
    ]
  },
  "work": [
    {
      "name": "Microsoft",
      "position": "Senior Customer Experience Engineer and Technical Lead, Reliability and Observability",
      "url": "https://www.microsoft.com/",
      "startDate": "2025-03",
      "summary": "Cross-product reliability and observability engineering across Azure services.",
      "highlights": [
        "Architected telemetry warehouse solutions using Azure Synapse, Microsoft Fabric and Azure Data Explorer.",
        "Defined an approach for exposing internal service indicators as reliability signals engineering teams and customers can use.",
        "Worked with engineering teams and Fortune 500 customers during complex production incidents."
      ]
    },
    {
      "name": "Microsoft",
      "position": "Senior Site Reliability Engineer, Azure Data",
      "url": "https://www.microsoft.com/",
      "startDate": "2023-09",
      "endDate": "2025-03",
      "summary": "Reliability strategy for Azure data services used by millions.",
      "highlights": [
        "Directed high-severity incident response and deep production troubleshooting.",
        "Helped introduce structured incident command and telemetry-led diagnosis across a multi-service portfolio.",
        "Contributed to an approximately 40% reduction in incident time-to-resolution."
      ]
    },
    {
      "name": "Microsoft",
      "position": "Senior Site Reliability Engineer, Localization as a Service",
      "url": "https://www.microsoft.com/",
      "startDate": "2019-09",
      "endDate": "2023-09",
      "summary": "Reliability, performance and operational efficiency for high-availability platforms supporting global Microsoft product workflows.",
      "highlights": [
        "Modernised infrastructure, monitoring and operational tooling across several Azure services.",
        "Built automation that improved deployment consistency and operational readiness."
      ]
    },
    {
      "name": "Microsoft",
      "position": "Software Engineer, Microsoft Ireland",
      "url": "https://www.microsoft.com/",
      "startDate": "2014-05",
      "endDate": "2019-09",
      "summary": "Software engineering across data processing, telemetry, localisation, validation and Office publishing systems.",
      "highlights": [
        "Built large-scale data-processing and telemetry systems for Microsoft Office engineering.",
        "Developed automation frameworks, workflow tooling and Azure-based internal services."
      ]
    }
  ],
  "education": [
    {
      "institution": "Griffith College",
      "area": "Systems and Principles",
      "studyType": "City & Guilds Diploma, NFQ Level 6",
      "startDate": "2013",
      "endDate": "2014"
    },
    {
      "institution": "Ballyfermot College of Further Education",
      "area": "Information Technology",
      "studyType": "FETAC Level 5 Certificate",
      "startDate": "2009",
      "endDate": "2010"
    }
  ],
  "skills": [
    {
      "name": "Software and distributed systems",
      "keywords": [
        "C#/.NET",
        "TypeScript",
        "SQL/T-SQL",
        "APIs",
        "Distributed systems",
        "CI/CD",
        "Automation"
      ]
    },
    {
      "name": "Production reliability",
      "keywords": [
        "Site Reliability Engineering",
        "High availability",
        "Incident command",
        "Production diagnosis",
        "SLI/SLO design",
        "Operational readiness"
      ]
    },
    {
      "name": "Data and observability",
      "keywords": [
        "Azure Data Explorer",
        "SQL Server",
        "PostgreSQL",
        "Microsoft Fabric",
        "Azure Synapse",
        "Telemetry platforms"
      ]
    },
    {
      "name": "Applied AI",
      "keywords": [
        "Agent workflows",
        "Model Context Protocol",
        "Durable state",
        "Retrieval",
        "Lineage",
        "Evaluation"
      ]
    }
  ],
  "projects": [
    {
      "name": "BarnPage",
      "description": "A deployed private workspace for riding barns with scheduling, barn-scoped access, lesson media and trainer-reviewed AI feedback.",
      "url": "https://barnpage.com/",
      "keywords": [
        "TypeScript",
        "Next.js",
        "PostgreSQL",
        "Azure"
      ]
    },
    {
      "name": "Agentic Data Kernel",
      "description": "An open-source persistence and workflow layer for durable agent state, causal lineage and controlled external effects.",
      "url": "https://github.com/Jason-Doyle/agentic-data-kernel",
      "keywords": [
        "TypeScript",
        "SQLite",
        "PostgreSQL",
        "MCP"
      ]
    }
  ],
  "publications": [
    {
      "name": "MCP Tool Readiness",
      "publisher": "Jason Doyle",
      "releaseDate": "2026-09-14",
      "url": "https://jasondoyle.ie/whitepapers/mcp-tool-readiness/",
      "summary": "A layered model for operational evidence, consumer policy and safe routing when agents select MCP tools dynamically."
    },
    {
      "name": "When the Endpoint Is Up but the Product Is Failing",
      "publisher": "Jason Doyle",
      "releaseDate": "2026-06-01",
      "url": "https://jasondoyle.ie/whitepapers/when-the-endpoint-is-up/",
      "summary": "A reliability model for AI products whose behaviour can fail while infrastructure remains available."
    },
    {
      "name": "Observability Is a Decision System",
      "publisher": "Jason Doyle",
      "releaseDate": "2026-05-01",
      "url": "https://jasondoyle.ie/whitepapers/observability-is-a-decision-system/",
      "summary": "Why telemetry creates value only when it improves a decision."
    }
  ],
  "meta": {
    "canonical": "https://jasondoyle.ie/engineering/",
    "version": "2026-09-14"
  }
}